© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 88837
    Prev
    Next
    INDEX
    Explanations

    feeling confident and secure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cord
    -0.09
     aspiration
    -0.09
    oro
    -0.09
    ª
    -0.09
    alin
    -0.09
    aso
    -0.09
    far
    -0.08
     allure
    -0.08
     erfahren
    -0.08
     clash
    -0.08
    POSITIVE LOGITS
     expressing
    0.16
     safety
    0.13
     trusting
    0.13
     experimenting
    0.12
     exploring
    0.12
     discussing
    0.12
     asking
    0.12
     knowing
    0.11
     entr
    0.11
     divul
    0.11
    Activations Density 0.054%

    No Known Activations